mesolitica/Malaysian-F5-TTS-Speech-Enhancement

Full Parameter Finetuning Malaysian Emilia F5-TTS Speech Enhancement

Continue training from SWivid/F5-TTS on post Speech-Enhancement Malaysian-Emilia-annotated

This model should be able to zero-shot voice conversion any Malaysian and Singaporean speakers.

WanDB at https://wandb.ai/huseinzol05/CFM-TTS

Checkpoints

We uploaded full checkpoints with optimizer states for each 50k steps at full-checkpoint.

If you found out the latest checkpoint is overfitting, we have also uploaded alternative checkpoints,

1. 150000 steps, huseinzol05/Malaysian-F5-TTS-150000
2. 200000 steps, huseinzol05/Malaysian-F5-TTS-200000
3. 250000 steps, huseinzol05/Malaysian-F5-TTS-250000

Dataset

We train on postfilter Malaysian-Emilia-annotated called Malaysian-Voice-Conversion-Speech-Enhancement

Source code

All source code at https://github.com/mesolitica/malaya-speech/tree/master/session/f5-tts